Skip to content
AI Atlas
PaperActive

DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injection in LLM Agents

arxiv.org/abs/2609.10892

quality89

Updated 1 h ago · first seen 11 Sept 2026

paper_01M294FQ9229VE7977EQJR07AQ

Published
11 Sept 2026
T1 · 1 h ago
arXiv
2609.10892
T1 · 1 h ago
Category
cs.CR
T1 · 1 h ago

Abstract

When an indirect prompt injection succeeds against an LLM agent, the compromise is visible in the agent's own behavior: a benign prefix of tool calls, a poisoned observation, and a suffix of actions that serve the attacker. An operator needs three facts: where the attack entered, which steps it corrupted, and whether apparent poison was resisted. Existing systems return either a whole-trace verdict or a single unsafe index. We present DriftNet, a dual-head trajectory Transformer that reads a logged tool-call trajectory and answers all three questions in one forward pass: one head classifies the trajectory as compromised or not, and a second assigns every step one of four labels (benign, injection point, hijacked, failed injection). To our knowledge it is the first supervised detector to produce this joint output. A frozen sentence encoder and four identity-free world features embed each step; the trained trunk, under two million parameters and optimized with a class-weighted joint objective over both heads, needs no access to the agent's model. On the task-disjoint split of the AgentDrift benchmark (12,536 trajectories, 71,024 labeled steps), with a 20-configuration sweep bounding hyperparameter sensitivity to 0.011 F1 and the test part evaluated exactly once, DriftNet reaches trajectory-level F1 of 0.983, exact injection-point recovery on 98.7% of attacked trajectories, hijacked-span IoU of 0.979, zero flags on 218 resisted attacks, and 2.9% flags on hard negatives. A surface baseline retrained on the identical split recovers 11.1% of partial hijacks and 17.1% of delayed executions; DriftNet reaches 98.6% and 93.2% while lowering every false-alarm rate. Reading all 26 residual errors shows that most misses trace to trajectories whose labeled injection observation carries no legible instruction, and we report the benchmark's measured world-identity regularity alongside the results.

Authors 2

Asif Pinjari, Mithun Paul Saint-Germain

Specification

Official page

Source:arXiv (Atom API + RSS)T1observed 1 h agohigh

Arxiv announce type
cross

Source:arXiv (Atom API + RSS)T1observed 1 h agohigh

arXiv id
2609.10892

Source:arXiv (Atom API + RSS)T1observed 1 h agohigh

Categories
cs.CR, cs.AI, cs.LG

Source:arXiv (Atom API + RSS)T1observed 1 h agohigh

PDF

Source:arXiv (Atom API + RSS)T1observed 1 h agohigh

Primary category
cs.CR

Source:arXiv (Atom API + RSS)T1observed 1 h agohigh

Published
11 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 1 h agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

1 h ago

Conflicts

None